]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/mgtv.py
d53d96aae1799e15d578c765545a929255009d31
2 from __future__
import unicode_literals
4 from .common
import InfoExtractor
5 from ..compat
import compat_str
6 from ..utils
import int_or_none
9 class MGTVIE(InfoExtractor
):
10 _VALID_URL
= r
'https?://(?:www\.)?mgtv\.com/(v|b)/(?:[^/]+/)*(?P<id>\d+)\.html'
14 'url': 'http://www.mgtv.com/v/1/290525/f/3116640.html',
15 'md5': 'b1ffc0fc163152acf6beaa81832c9ee7',
19 'title': '我是歌手第四季双年巅峰会:韩红李玟“双王”领军对抗',
20 'description': '我是歌手第四季双年巅峰会',
22 'thumbnail': r
're:^https?://.*\.jpg$',
25 'url': 'http://www.mgtv.com/b/301817/3826653.html',
26 'only_matching': True,
29 def _real_extract(self
, url
):
30 video_id
= self
._match
_id
(url
)
31 api_data
= self
._download
_json
(
32 'http://pcweb.api.mgtv.com/player/video', video_id
,
33 query
={'video_id': video_id
},
34 headers
=self
.geo_verification_headers())['data']
35 info
= api_data
['info']
36 title
= info
['title'].strip()
37 stream_domain
= api_data
['stream_domain'][0]
40 for idx
, stream
in enumerate(api_data
['stream']):
41 stream_path
= stream
.get('url')
44 format_data
= self
._download
_json
(
45 stream_domain
+ stream_path
, video_id
,
46 note
='Download video info for format #%d' % idx
)
47 format_url
= format_data
.get('info')
50 tbr
= int_or_none(self
._search
_regex
(
51 r
'_(\d+)_mp4/', format_url
, 'tbr', default
=None))
53 'format_id': compat_str(tbr
or idx
),
57 'protocol': 'm3u8_native',
59 self
._sort
_formats
(formats
)
65 'description': info
.get('desc'),
66 'duration': int_or_none(info
.get('duration')),
67 'thumbnail': info
.get('thumb'),